© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66904
    Prev
    Next
    INDEX
    Explanations

    credit unions and storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    some
    -2.48
    
    -2.27
     vollständige
    -1.90
    something
    -1.88
    
    -1.78
     wichtige
    -1.71
     verbess
    -1.70
     genaue
    -1.70
    üenza
    -1.68
     espectro
    -1.68
    POSITIVE LOGITS
     were
    1.80
     ustedes
    1.70
     extraordinaire
    1.66
     unſ
    1.62
    ⢊
    1.61
    ？
    1.60
    ou
    1.59
    ⬍
    1.58
    »،
    1.56
     respectivos
    1.56
    Activations Density 0.004%

    No Known Activations